GLM-5-Turbo

Released

GLM-5-Turbo is an AI model released by Z.ai on Sunday, Mar 15 2026, 32 days after GLM-5. It has a 200k token context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider.. Benchmark results (shown below) cover ZClawBench, and BullshitBench v2.

Benchmarks

Agentic & tool use

ZClawBenchOpenClaw task performance — mean task score on a zero-to-one scale across 116 OpenClaw tasksvia Z.ai ZClawBench
0.564

Robustness

BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better.via BullshitBench
31%
#68 of 107

Compare GLM-5-Turbo with

GLM-5-Turbo

About

GLM-5-Turbo was announced in March 2026 as a hosted language model trained for OpenClaw workflows. Zhipu AI focused on following multi-step instructions, calling tools reliably, and resuming work across long tasks.

Zhipu reported an average score of 0.564 out of 1 across 116 ZClawBench tasks, including information retrieval, software development and data analysis. The API supported function calls, a 200K context and multiple thinking settings.

Frequently asked questions

GLM-5-Turbo was released by Z.ai on Sunday, Mar 15 2026.

All Z.ai releases

24 tracked